Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Lost in Back-Translation : Emotion Preservation in Neural Machine Translation

Publication

Lost in Back-Translation : Emotion Preservation in Neural Machine Translation

Troiano, Enrica; Klinger, Roman; Padó, Sebastian (2020): Lost in Back-Translation : Emotion Preservation in Neural Machine Translation, in: Donia Scott, Nuria Bell, Chengqing Zong, u. a. (Hrsg.), Proceedings of the 28th International Conference on Computational Linguistics, International Committee on Computational Linguistics, S. 4340–4354, doi: 10.18653/v1/2020.coling-main.384.

Details

Faculty/Chair
Faculty/Professorship
Author
Troiano, Enrica
Padó, Sebastian
Title of the compilation
Proceedings of the 28th International Conference on Computational Linguistics
Editors
Scott, Donia
Bell, Nuria
Zong, Chengqing
Conference
28th International Conference on Computational Linguistics, Barcelona, Spain (Online)
Publisher Information
International Committee on Computational Linguistics
Year of publication
2020
Language
English
DOI
Abstract

Machine translation provides powerful methods to convert text between languages, and is therefore a technology enabling a multilingual world. An important part of communication, however, takes place at the non-propositional level (e.g., politeness, formality, emotions), and it is far from clear whether current MT methods properly translate this information. This paper investigates the specific hypothesis that the non-propositional level of emotions is at least partially lost in MT. We carry out a number of experiments in a back-translation setup and establish that (1) emotions are indeed partially lost during translation; (2) this tendency can be reversed almost completely with a simple re-ranking approach informed by an emotion classifier, taking advantage of diversity in the n-best list; (3) the re-ranking approach can also be applied to change emotions, obtaining a model for emotion style transfer. An in-depth qualitative analysis reveals that there are recurring linguistic changes through which emotions are toned down or amplified, such as change of modality.

GND Keywords
Computerlinguistik
Emotion
Keywords
Emotion Preservation
DDC Classification
004 Computer science
RVK Classification
ST 306
Type
Conferenceobject
URI
Activation date
2024-03-14
Project(s)

Permalink: https://fis.uni-bamberg.de/handle/uniba/93906 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.